Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Stories to Cities to Games: A Qualitative Evaluation of Behaviour Planning

Mustafa F. Abdelwahed, Joan Espasa, Alice Toniolo, Ian P. Gent

TL;DR

The paper addresses the need for generating multiple, qualitatively distinct plans rather than a single solution. It advances behaviour planning by introducing the Behaviour Sorts Suite (BSS) to define a behaviour space and the FBI (Forbid Behaviour Iterative) family of planners, including FBI_SMT (model-based) and FBI_LTL (model-free), and demonstrates their applicability across storytelling, urban planning, and game evaluation. The results show that behaviour planning can produce diverse narratives, layouts, and player traces, enabling users to compare qualitatively different options. This domain-agnostic framework integrates diversity into the planning process, facilitating varied outcomes and strategic decision-making, with future work focusing on automating behaviour-space construction from data or feedback.

Abstract

The primary objective of a diverse planning approach is to generate a set of plans that are distinct from one another. Such an approach is applied in a variety of real-world domains, including risk management, automated stream data analysis, and malware detection. More recently, a novel diverse planning paradigm, referred to as behaviour planning, has been proposed. This approach extends earlier methods by explicitly incorporating a diversity model into the planning process and supporting multiple planning categories. In this paper, we demonstrate the usefulness of behaviour planning in real-world settings by presenting three case studies. The first case study focuses on storytelling, the second addresses urban planning, and the third examines game evaluation.

From Stories to Cities to Games: A Qualitative Evaluation of Behaviour Planning

TL;DR

The paper addresses the need for generating multiple, qualitatively distinct plans rather than a single solution. It advances behaviour planning by introducing the Behaviour Sorts Suite (BSS) to define a behaviour space and the FBI (Forbid Behaviour Iterative) family of planners, including FBI_SMT (model-based) and FBI_LTL (model-free), and demonstrates their applicability across storytelling, urban planning, and game evaluation. The results show that behaviour planning can produce diverse narratives, layouts, and player traces, enabling users to compare qualitatively different options. This domain-agnostic framework integrates diversity into the planning process, facilitating varied outcomes and strategic decision-making, with future work focusing on automating behaviour-space construction from data or feedback.

Abstract

The primary objective of a diverse planning approach is to generate a set of plans that are distinct from one another. Such an approach is applied in a variety of real-world domains, including risk management, automated stream data analysis, and malware detection. More recently, a novel diverse planning paradigm, referred to as behaviour planning, has been proposed. This approach extends earlier methods by explicitly incorporating a diversity model into the planning process and supporting multiple planning categories. In this paper, we demonstrate the usefulness of behaviour planning in real-world settings by presenting three case studies. The first case study focuses on storytelling, the second addresses urban planning, and the third examines game evaluation.
Paper Structure (11 sections, 2 equations, 7 figures, 1 algorithm)

This paper contains 11 sections, 2 equations, 7 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background
  3. Planning Problem
  4. Diversity Model and Behaviour Count
  5. Diversity Planning Problem
  6. Behaviour Planning
  7. Case Studies
  8. Storytelling
  9. Urban Planning
  10. Game Evaluation
  11. Conclusions & Future work

Figures (7)

  • Figure 1: Three diverse narratives for the Aladdin world.
  • Figure 2: Behaviour space for the Aladdin story domain, illustrating how different narrative outcomes map to distinct behaviours.
  • Figure 3: A simple illustration of the urban planning simulator operation.
  • Figure 4: Urban plans for the town of St Andrews. Red color means commercial zone, purple means facility zone, green means green space zone, and blue means residential zone
  • Figure 5: Behaviour space used to generate the urban plans presented in \ref{['fig:urban-plans-st-andrews']}. Behaviour space is the gird represented on the left, while the categorical range is shown on the right.
  • ...and 2 more figures

Theorems & Definitions (2)

  • Definition 1: Planning Problem
  • Definition 2: Diversity Planning Problem